Data augmentation and image understanding

12/28/2020
by   Alex Hernández-García, et al.
0

Interdisciplinary research is often at the core of scientific progress. This dissertation explores some advantageous synergies between machine learning, cognitive science and neuroscience. In particular, this thesis focuses on vision and images. The human visual system has been widely studied from both behavioural and neuroscientific points of view, as vision is the dominant sense of most people. In turn, machine vision has also been an active area of research, currently dominated by the use of artificial neural networks. This work focuses on learning representations that are more aligned with visual perception and the biological vision. For that purpose, I have studied tools and aspects from cognitive science and computational neuroscience, and attempted to incorporate them into machine learning models of vision. A central subject of this dissertation is data augmentation, a commonly used technique for training artificial neural networks to augment the size of data sets through transformations of the images. Although often overlooked, data augmentation implements transformations that are perceptually plausible, since they correspond to the transformations we see in our visual world – changes in viewpoint or illumination, for instance. Furthermore, neuroscientists have found that the brain invariantly represents objects under these transformations. Throughout this dissertation, I use these insights to analyse data augmentation as a particularly useful inductive bias, a more effective regularisation method for artificial neural networks, and as the framework to analyse and improve the invariance of vision models to perceptually plausible transformations. Overall, this work aims to shed more light on the properties of data augmentation and demonstrate the potential of interdisciplinary research.

READ FULL TEXT
research
06/11/2019

Learning robust visual representations using data augmentation invariance

Deep convolutional neural networks trained for image object categorizati...
research
10/11/2018

Efficient Augmentation via Data Subsampling

Data augmentation is commonly used to encode invariances in learning met...
research
09/18/2018

Albumentations: fast and flexible image augmentations

Data augmentation is a commonly used technique for increasing both the s...
research
06/07/2021

Rotating spiders and reflecting dogs: a class conditional approach to learning data augmentation distributions

Building invariance to non-meaningful transformations is essential to bu...
research
04/16/2021

Probing artificial neural networks: insights from neuroscience

A major challenge in both neuroscience and machine learning is the devel...
research
02/14/2022

Testing the Tools of Systems Neuroscience on Artificial Neural Networks

Neuroscientists apply a range of common analysis tools to recorded neura...
research
10/10/2020

Category-Learning with Context-Augmented Autoencoder

Finding an interpretable non-redundant representation of real-world data...

Please sign up or login with your details

Forgot password? Click here to reset